Machine Learning for Sustainable Energy Transition
The Machine Learning Group at ULB specializes in developing cutting-edge intelligent systems that address key challenges in energy transition. Our team leverages advanced data analytics, time series forecasting, and machine learning to enable smarter, more resilient, and decentralized energy systems for urban environments.
Call for Research Partners: Urban Energy Transition
We’re seeking partners for the INNOVIRIS Research Platform 2026 call on sustainable energy transition in urban environments. This call invites academic consortiums to conduct collaborative, transdisciplinary research aimed at transforming current energy systems toward more sustainable, equitable, and resilient alternatives in urban settings, with special focus on the Brussels-Capital Region.
Sample Research Themes:
- Urban Geothermal & Solar Integration: ML-based optimization of locations, performance forecasting, and adaptive infrastructure design.
- Urban Heat Recovery Systems: Identifying and ranking potential waste heat sources and designing adaptive heat exchange networks.
- District Wind Energy & Digital Twins: Optimizing siting and operation of compact wind turbines with ML-enhanced wind flow modeling.
- Microgrids & Decentralized Energy: Real-time optimization of local energy systems with ML-powered management systems.
- Predictive Maintenance for Urban Renewables: ML-based digital twins for system health monitoring and anomaly detection.
- Integrated Urban Energy System Orchestration: Developing unified control architectures for coordinating geothermal, solar, wind, and heat recovery systems.
Partner Requirements: The consortium must include at least one public institution, non-profit organization, or independent business based in Brussels.
Key Collaborations
Università degli Studi del Sannio
Our ongoing collaboration with UniSannio focuses on developing advanced machine learning models for electrical grid optimization and renewable energy integration in urban environments.
TRAIL Ecosystem
As a proud member of the TRAIL (Trusted AI Labs) Ecosystem, we collaborate with leading Belgian AI research groups to develop responsible and innovative machine learning solutions for sustainable energy systems.
Areas of Expertise
Renewable Energy Forecasting
Developing state-of-the-art predictive models for wind and solar power generation to enable efficient integration of renewable energy sources in urban grids.
Energy Load Prediction
Creating accurate short and medium-term electricity demand forecasting systems to optimize grid management and energy market participation.
Grid Optimization
Designing intelligent systems that enhance grid flexibility and reliability through dynamic line rating and adaptive management approaches.
Digital Twin Technology
Building virtual representations of physical energy infrastructure to simulate, optimize, and monitor real-time performance for enhanced decision-making.
Energy Storage Optimization
Developing strategies for optimal utilization of battery storage and other energy storage technologies in conjunction with renewable generation.
Transfer Learning Applications
Applying novel transfer learning techniques to reduce sensor deployment costs and enable affordable large-scale energy infrastructure monitoring.
Research Publications
2025 – Improving Ramp Forecasting Accuracy under Class Imbalance [Under Review]
Authors: Morales-Hernández A., De Caro F., Paldino G.M., Tribel P., Vaccaro A., Bontempi G.
This research addresses the challenge of predicting sudden changes in wind power generation (ramp events). Our approach formulates the problem as a multivariate time series classification task and proposes a novel data preprocessing strategy to handle class imbalance, achieving over 85% accuracy.
2025 – A Novel Dual-CNN Architecture with Adaptive Persistence for Medium-Term Electricity Load Forecasting [Under Review]
Authors: Tribel P., Paldino G.M., Morales Hernández A., Bontempi G.
This paper introduces a dual-CNN architecture for 30-hour ahead electricity load forecasting. The model combines two parallel CNNs to process historical load and meteorological data, consistently outperforming operational forecasts by 20.47% on average.
2024 – PyAWD: A Library for Generating Large Synthetic Datasets of Acoustic Wave Propagation with Devito
Authors: Tribel P., Bontempi G.
This paper introduces PyAWD, a Python library for generating high-resolution synthetic datasets simulating acoustic wave propagation. It enables the creation of customizable simulations to train ML models that can retrieve epicenter locations with minimal sensor data.
2022 – Online learning of windmill time series using Long Short-term Cognitive Networks
Authors: Morales-Hernández A., Nápoles G., Jastrzebska A., Salgueiro Y., Vanhoof K.
This research introduces Long Short-term Cognitive Networks (LSTCNs) for forecasting windmill time series in online learning settings, achieving lower forecasting errors and significantly faster training and testing times.
Current Projects
Transfer Learning for Smart Grid Monitoring
Development of transfer learning methodologies to reduce the number of required temperature sensors in power transmission lines, enabling cost-effective implementation of Dynamic Thermal Rating systems across urban grid infrastructure.
Adaptive Forecasting for Renewable Integration
Implementation of ensemble-based forecasting systems that combine multiple prediction models to improve accuracy and stability for wind and solar energy production, adapting to changing environmental conditions in urban settings.
Virtual Power Plant Simulator
Development of a simulation platform that generates synthetic weather, solar, and wind data, along with grid load and market prices, to train models for forecasting and optimizing battery management strategies.
Get in Touch
If you have a project you’d like to discuss or any questions, feel free to reach out to us:
Prof. Gianluca Bontempi
Co-director, Machine Learning Group, ULB
Email: gianluca.bontempi@ulb.be
Dr. Natalia García-Colín
Research and Innovation Manager, Machine Learning Group, ULB
Email: natalia.garcia.colin@ulb.be